Change Detection and Image Time-Series Analysis 1: Unervised Methods

By Abdourrahmane M Atto

Change Detection and Image Time Series Analysis 1 presents a wide range of unsupervised methods for temporal evolution analysis through the use of image time series associated with optical and/or synthetic aperture radar acquisition modalities.

Chapter 1 introduces two unsupervised approaches to multiple-change detection in bi-temporal multivariate images, with Chapters 2 and 3 addressing change detection in image time series in the context of the statistical analysis of covariance matrices. Chapter 4 focuses on wavelets and convolutional-neural filters for feature extraction and entropy-based anomaly detection, and Chapter 5 deals with a number of metrics such as cross correlation ratios and the Hausdorff distance for variational analysis of the state of snow. Chapter 6 presents a fractional dynamic stochastic field model for spatio temporal forecasting and for monitoring fast-moving meteorological events such as cyclones. Chapter 7 proposes an analysis based on characteristic points for texture modeling, in the context of graph theory, and Chapter 8 focuses on detecting new land cover types by classification-based change detection or feature/pixel based change detection. Chapter 9 focuses on the modeling of classes in the difference image and derives a multiclass model for this difference image in the context of change vector analysis.

• Format: Hardcover
• Language: English
• ISBN: 178945056X
• ISBN13: 9781789450569
• Release Date: January 2022
• Publisher: Wiley-Iste
• Length: 304 Pages
• Weight: 1.32 lbs.
• Dimensions: 0.7" x 6.1" x 9.2"